Matches in SemOpenAlex for { <https://semopenalex.org/work/W4310922437> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W4310922437 abstract "The long-standing theory that a colour-naming system evolves under dual pressure of efficient communication and perceptual mechanism is supported by more and more linguistic studies, including analysing four decades of diachronic data from the Nafaanra language. This inspires us to explore whether machine learning could evolve and discover a similar colour-naming system via optimising the communication efficiency represented by high-level recognition performance. Here, we propose a novel colour quantisation transformer, CQFormer, that quantises colour space while maintaining the accuracy of machine recognition on the quantised images. Given an RGB image, Annotation Branch maps it into an index map before generating the quantised image with a colour palette; meanwhile the Palette Branch utilises a key-point detection way to find proper colours in the palette among the whole colour space. By interacting with colour annotation, CQFormer is able to balance both the machine vision accuracy and colour perceptual structure such as distinct and stable colour distribution for discovered colour system. Very interestingly, we even observe the consistent evolution pattern between our artificial colour system and basic colour terms across human languages. Besides, our colour quantisation method also offers an efficient quantisation method that effectively compresses the image storage while maintaining high performance in high-level recognition tasks such as classification and detection. Extensive experiments demonstrate the superior performance of our method with extremely low bit-rate colours, showing potential to integrate into quantisation network to quantities from image to network activation. The source code is available at https://github.com/ryeocthiv/CQFormer" @default.
- W4310922437 created "2022-12-21" @default.
- W4310922437 creator A5007550435 @default.
- W4310922437 creator A5016680184 @default.
- W4310922437 creator A5023756404 @default.
- W4310922437 creator A5032080056 @default.
- W4310922437 creator A5035551115 @default.
- W4310922437 creator A5042711470 @default.
- W4310922437 creator A5059094652 @default.
- W4310922437 creator A5087989444 @default.
- W4310922437 date "2022-12-06" @default.
- W4310922437 modified "2023-10-17" @default.
- W4310922437 title "Name Your Colour For the Task: Artificially Discover Colour Naming via Colour Quantisation Transformer" @default.
- W4310922437 doi "https://doi.org/10.48550/arxiv.2212.03434" @default.
- W4310922437 hasPublicationYear "2022" @default.
- W4310922437 type Work @default.
- W4310922437 citedByCount "0" @default.
- W4310922437 crossrefType "posted-content" @default.
- W4310922437 hasAuthorship W4310922437A5007550435 @default.
- W4310922437 hasAuthorship W4310922437A5016680184 @default.
- W4310922437 hasAuthorship W4310922437A5023756404 @default.
- W4310922437 hasAuthorship W4310922437A5032080056 @default.
- W4310922437 hasAuthorship W4310922437A5035551115 @default.
- W4310922437 hasAuthorship W4310922437A5042711470 @default.
- W4310922437 hasAuthorship W4310922437A5059094652 @default.
- W4310922437 hasAuthorship W4310922437A5087989444 @default.
- W4310922437 hasBestOaLocation W43109224371 @default.
- W4310922437 hasConcept C111919701 @default.
- W4310922437 hasConcept C121332964 @default.
- W4310922437 hasConcept C153180895 @default.
- W4310922437 hasConcept C154945302 @default.
- W4310922437 hasConcept C165801399 @default.
- W4310922437 hasConcept C2776321320 @default.
- W4310922437 hasConcept C2779674283 @default.
- W4310922437 hasConcept C31972630 @default.
- W4310922437 hasConcept C41008148 @default.
- W4310922437 hasConcept C62520636 @default.
- W4310922437 hasConcept C66322947 @default.
- W4310922437 hasConcept C82990744 @default.
- W4310922437 hasConceptScore W4310922437C111919701 @default.
- W4310922437 hasConceptScore W4310922437C121332964 @default.
- W4310922437 hasConceptScore W4310922437C153180895 @default.
- W4310922437 hasConceptScore W4310922437C154945302 @default.
- W4310922437 hasConceptScore W4310922437C165801399 @default.
- W4310922437 hasConceptScore W4310922437C2776321320 @default.
- W4310922437 hasConceptScore W4310922437C2779674283 @default.
- W4310922437 hasConceptScore W4310922437C31972630 @default.
- W4310922437 hasConceptScore W4310922437C41008148 @default.
- W4310922437 hasConceptScore W4310922437C62520636 @default.
- W4310922437 hasConceptScore W4310922437C66322947 @default.
- W4310922437 hasConceptScore W4310922437C82990744 @default.
- W4310922437 hasLocation W43109224371 @default.
- W4310922437 hasOpenAccess W4310922437 @default.
- W4310922437 hasPrimaryLocation W43109224371 @default.
- W4310922437 hasRelatedWork W2004761075 @default.
- W4310922437 hasRelatedWork W2263699433 @default.
- W4310922437 hasRelatedWork W2331165631 @default.
- W4310922437 hasRelatedWork W2361861616 @default.
- W4310922437 hasRelatedWork W2368237188 @default.
- W4310922437 hasRelatedWork W2377979023 @default.
- W4310922437 hasRelatedWork W2384383935 @default.
- W4310922437 hasRelatedWork W2509410833 @default.
- W4310922437 hasRelatedWork W3183827559 @default.
- W4310922437 hasRelatedWork W4234082839 @default.
- W4310922437 isParatext "false" @default.
- W4310922437 isRetracted "false" @default.
- W4310922437 workType "article" @default.